by Garybot126

Freely switch between the models and intensity used by subagents in DSH

by QI-seven33

Optional JEV decision mode for DeepSeek Harness Desktop: deterministic reads, bounded semantic selection, native authorization and credential UI.

by KIDLi1412

GitHub-style daily token-usage heatmap on the new-session screen with a selectable calendar-year view, green/blue color schemes, and today / this-month / all-time totals.

by sanser9

Brings the free models of a locally installed OpenCode CLI into DSH: starts or reuses a local opencode serve, discovers the live catalog and refreshes it every five minutes, and bridges the session ev

by xinghe-1018

Balance badge that follows the active model provider: official readings for DeepSeek, Qwen Token Plan and Aliyun BSS, plus Moonshot and OpenRouter endpoints not yet key-verified.

by fufuf-c

Local token usage and cost dashboard for DeepSeek Harness: four-segment token breakdown (miss/cache-hit/cache-write/output), cache savings estimate against the miss/hit price gap, per-session drill-do

by quan-v

MCP server configuration UI plugin for DeepSeek Harness (made in DeepSeek Harness)

Token usage statistics by model, session and date in a sidebar panel, plus OpenCode Go quota, DeepSeek balance and Z.ai quota monitoring.

by qjf44

One-click OpenAI-compatible API (CodeBuddy/vLLM/proxies) with thinking mode, avoiding developer-role content_filter rejection.

by linziyanleo

Configure custom LLM providers in DeepSeek Harness.

by llmpolska

Tiered model routing for DeepSeek Harness: think/build model tiers, vision delegation (the vision model only describes images; the working model acts), image generation, and a high-impact guard.

by w2327644822-png

Personal usage analytics & activity dashboard for the DeepSeek Harness (dsh) web GUI: token totals, contribution heatmap, model share, insights. Local-only, metadata only.

by moon16u

A pouch of practical micro-plugins for DSH: per-turn wall-clock time injection, safe restart, session ID header badge, Tavily search provider, configurable LLM request-header routes, and an MCP server

by imMamdouhaboammar

Use ChatGPT and Codex subscriptions in DeepSeek Harness with OAuth, quota runway forecast, safe resets, web search, image generation, and Fast mode.

by Ztyss

Fully take over model services, and provide an intuitive configuration approach with quota display

by Sttrevens

Per-turn USD cost badge in the Web UI: session total in the header and per-turn cost in each message footer, with a hover breakdown.

by FelixJiashengFu

Mighty mode: The DeepSeek Harness plugin, a single luxury-gold switch that maxes out the reasoning intensity and output budget at every step · Max-effort mode switch for DeepSeek Harness

by huangyuheng

Real-time Token Usage Dashboard · Real-time token usage dashboard for DeepSeek Harness — live totals, filters by model/day/month/project, smooth trend chart.

by 6pofx

DSH (DeepSeek Harness) Skills and MCP Management Console Plugin: Hierarchically browse all loaded skills by source, independently toggle model/user invocations, create/edit/delete skills (recoverable from trash), batch install multiple selections from GitHub; add, delete, and update MCP servers, with status monitoring and connection testing.

by QGG4588

DSH automatic model failover · provider-pool failover: on rate limit/quota/timeout, auto-retry with the next untried model from the selected providers' full model pools. Runtime tool: model_failover + Web UI panel.

by dyuan311

ChatGPT subscription OAuth for the openai-codex provider in DeepSeek Harness

by a2580vb

DeepSeek Harness LLM adapter for OpenCode Go (opencode.ai/zen): /models discovery with cache, three wire protocols (OpenAI Responses, OpenAI-compatible Chat Completions, Anthropic Messages), tool calling, reasoning mapping, streaming, and the required x-opencode-session affinity header.

by iasiv5

DSH Plugin: Adds web device code login / logout entry points to DSH's built-in GitHub Copilot channel, pre-configures out-of-the-box Provider routes, and supports model list management.

by Movingelated

DSH (DeepSeek Harness) plugin: delegate read-only collection tasks to a local Ollama model — zero cloud token cost, zero API key. Delegate read-only collection tasks to a local Ollama model: includes settings panel + selection guide + AI-readable manual.